Multi-provider AGENTS.md generator and ExecPlan harness for coding agents.
agentrules-architect is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo clone trevor-nichols/agentrules-architectOpen or clone the template repository.
Move the relevant AGENTS.md content into your project root.
Update project-specific commands, environment rules, and sensitive areas.
Repository setup guidance
Strong trust signals; still review the README and permissions before production use.
Last commit was about 99 days ago.
122 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
3 security/trust notes recorded.
Setup difficulty is 3/5.
A drop-in AGENTS.md file that makes coding agents behave like senior engineers, eliminating sycophancy and forcing verification.
Convert and sync AI coding-agent rule files between formats with zero dependencies.
Curated AI coding agent skills and playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKILL.md-compatible tools.
A CLI tool to package and deploy consistent AI coding environments across multiple assistants.
AgentRules Architect analyzes a code repository and generates AGENTS.md or CLAUDE.md files that guide AI coding agents. It uses a six-phase pipeline with support for multiple AI providers like OpenAI, Anthropic, and Google. The tool also includes ExecPlan for managing long-running agent tasks.
AgentRules Architect is a comprehensive tool for generating agent rules files (AGENTS.md, CLAUDE.md) and managing execution plans for AI coding agents. It features a six-phase analysis pipeline: discovery, planning, deep dives, synthesis, consolidation, and final generation. The tool supports multiple AI providers including OpenAI (Codex), Anthropic (Claude Code), Google Gemini, DeepSeek, and xAI. It provides a rich CLI with persistent TOML configuration, provider-specific request adapters, local runtime integrations (Codex app-server, Claude Code), and optional planning artifacts. Key features include Tavily web search integration for researcher agents, Rich terminal UI with real-time progress, configurable outputs (AGENTS.md, SNAPSHOT.md, .cursorignore, scaffold templates), and ExecPlan commands for deterministic long-running work. The project is MIT-licensed and actively maintained.
122
Stars
18
Forks
0
Issues
MIT
License
Multi-provider AGENTS.md generator and ExecPlan harness for coding agents.
Developers using AI coding agents like Codex, Claude Code, or Cursor., Open-source maintainers who want to standardize agent behavior in their repositories., Teams adopting AI-assisted development workflows.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
API keys for multiple providers are stored in a local config file; ensure file permissions are restricted. Tavily web search integration sends queries to an external service; review data privacy policies.
Similar or complementary options to evaluate include agents-md, agentsync, ok-skills.
Aug 20, 2026